From f7e0efc9b50266f5317b50732efff98d40fc879a Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 17 Jun 2016 18:33:00 +0100 Subject: [PATCH 1/5] arm64: update ASID limit During a rollover, we mark the active ASID on each CPU as reserved, before allocating a new ID for the task that caused the rollover. This means that with N CPUs, we can only guarantee the new task to obtain a valid ASID if we have at least N+1 ASIDs. Update this limit in the initcall check. Note that this restriction was introduced by commit 8e648066 on the arch/arm side, which disallow re-using the previously active ASID on the local CPU, as it would introduce a TLB race. In addition, we only dispose of NUM_USER_ASIDS-1, since ASID 0 is reserved. Add this restriction as well. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- arch/arm64/mm/context.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index b7b397802088..efcf1f7ef1e4 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) &asid_generation); flush_context(cpu); - /* We have at least 1 ASID per CPU, so this will always succeed */ + /* We have more ASIDs than CPUs, so this will always succeed */ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); set_asid: @@ -227,8 +227,11 @@ switch_mm_fastpath: static int asids_init(void) { asid_bits = get_cpu_asid_bits(); - /* If we end up with more CPUs than ASIDs, expect things to crash */ - WARN_ON(NUM_USER_ASIDS < num_possible_cpus()); + /* + * Expect allocation after rollover to fail if we don't have at least + * one more ASID than CPUs. ASID #0 is reserved for init_mm. + */ + WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus()); atomic64_set(&asid_generation, ASID_FIRST_VERSION); asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map), GFP_KERNEL); From 9ca4e58c20d5cb2a5bc378238188c71317aceac5 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 21 Jun 2016 10:44:00 +0900 Subject: [PATCH 2/5] arm64: fix boot image dependencies to not generate invalid images I fixed boot image dependencies for arch/arm in commit 3939f3345050 ("ARM: 8418/1: add boot image dependencies to not generate invalid images"). I see a similar problem for arch/arm64; "make -jN Image Image.gz" would sometimes end up generating bad images where N > 1. Fix the dependency in arch/arm64/Makefile to avoid the race between "make Image" and "make Image.*". Acked-by: Catalin Marinas Signed-off-by: Masahiro Yamada Signed-off-by: Will Deacon --- arch/arm64/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 7085e322dc42..648a32c89541 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -95,7 +95,7 @@ boot := arch/arm64/boot Image: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ -Image.%: vmlinux +Image.%: Image $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ zinstall install: From 20c27a4270c775d7ed661491af8ac03264d60fc6 Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Tue, 21 Jun 2016 15:32:57 +0800 Subject: [PATCH 3/5] arm64: mm: remove page_mapping check in __sync_icache_dcache __sync_icache_dcache unconditionally skips the cache maintenance for anonymous pages, under the assumption that flushing is only required in the presence of D-side aliases [see 7249b79f6b4cc ("arm64: Do not flush the D-cache for anonymous pages")]. Unfortunately, this breaks migration of anonymous pages holding self-modifying code, where userspace cannot be reasonably expected to reissue maintenance instructions in response to a migration. This patch fixes the problem by removing the broken page_mapping(page) check from the cache syncing code, otherwise we may end up fetching and executing stale instructions from the PoU. Cc: Catalin Marinas Cc: Will Deacon Cc: Mark Rutland Cc: Reviewed-by: Catalin Marinas Signed-off-by: Shaokun Zhang Signed-off-by: Will Deacon --- arch/arm64/mm/flush.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index dbd12ea8ce68..43a76b07eb32 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr) { struct page *page = pte_page(pte); - /* no flushing needed for anonymous pages */ - if (!page_mapping(page)) - return; - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) sync_icache_aliases(page_address(page), PAGE_SIZE << compound_order(page)); From 5c492c3f5255bd34f7ff8867515ecf98dcba2a2e Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 22 Jun 2016 10:06:12 +0100 Subject: [PATCH 4/5] arm64: smp: Add function to determine if cpus are stuck in the kernel kernel/smp.c has a fancy counter that keeps track of the number of CPUs it marked as not-present and left in cpu_park_loop(). If there are any CPUs spinning in here, features like kexec or hibernate may release them by overwriting this memory. This problem also occurs on machines using spin-tables to release secondary cores. After commit 44dbcc93ab67 ("arm64: Fix behavior of maxcpus=N") we bring all known cpus into the secondary holding pen, meaning this memory can't be re-used by kexec or hibernate. Add a function cpus_are_stuck_in_kernel() to determine if either of these cases have occurred. Signed-off-by: James Morse Acked-by: Mark Rutland Reviewed-by: Suzuki K Poulose Signed-off-by: Will Deacon --- arch/arm64/include/asm/smp.h | 12 ++++++++++++ arch/arm64/kernel/smp.c | 18 ++++++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 433e50405274..022644704a93 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void) cpu_park_loop(); } +/* + * If a secondary CPU enters the kernel but fails to come online, + * (e.g. due to mismatched features), and cannot exit the kernel, + * we increment cpus_stuck_in_kernel and leave the CPU in a + * quiesecent loop within the kernel text. The memory containing + * this loop must not be re-used for anything else as the 'stuck' + * core is executing it. + * + * This function is used to inhibit features like kexec and hibernate. + */ +bool cpus_are_stuck_in_kernel(void); + #endif /* ifndef __ASSEMBLY__ */ #endif /* ifndef __ASM_SMP_H */ diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 678e0842cb3b..62ff3c0622e2 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -909,3 +909,21 @@ int setup_profiling_timer(unsigned int multiplier) { return -EINVAL; } + +static bool have_cpu_die(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + int any_cpu = raw_smp_processor_id(); + + if (cpu_ops[any_cpu]->cpu_die) + return true; +#endif + return false; +} + +bool cpus_are_stuck_in_kernel(void) +{ + bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die()); + + return !!cpus_stuck_in_kernel || smp_spin_tables; +} From d74b4e4f1a6dbe27acce723e071c86a6ed154bf2 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 22 Jun 2016 10:06:13 +0100 Subject: [PATCH 5/5] arm64: hibernate: Don't hibernate on systems with stuck CPUs Hibernate relies on cpu hotplug to prevent secondary cores executing the kernel text while it is being restored. Add a call to cpus_are_stuck_in_kernel() to determine if there are CPUs not counted by 'num_online_cpus()', and prevent hibernate in this case. Fixes: 82869ac57b5 ("arm64: kernel: Add support for hibernate/suspend-to-disk") Acked-by: Mark Rutland Signed-off-by: James Morse Signed-off-by: Will Deacon --- arch/arm64/kernel/hibernate.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f8df75d740f4..21ab5df9fa76 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -236,6 +237,11 @@ int swsusp_arch_suspend(void) unsigned long flags; struct sleep_stack_data state; + if (cpus_are_stuck_in_kernel()) { + pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n"); + return -EBUSY; + } + local_dbg_save(flags); if (__cpu_suspend_enter(&state)) {